© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56767
    Prev
    Next
    INDEX
    Explanations

    worker rights and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ty
    -0.10
    ãģ£ãģįãĤĬ
    -0.10
    å·²ä¹ħçļĦ
    -0.10
    ÙĪاÙĨ
    -0.09
    åħ¬å¸ĥ
    -0.09
    ance
    -0.09
    ä»İ严治
    -0.09
    è¿ĽåĨĽ
    -0.09
     ÐłÐ¾Ñģ
    -0.09
    å°Ķæĸ¯
    -0.09
    POSITIVE LOGITS
    hip
    0.09
    enheim
    0.09
    代表大ä¼ļ
    0.09
    horse
    0.09
    éĺ¿å§¨
    0.09
     Alic
    0.09
    aje
    0.09
     Revel
    0.08
    ени
    0.08
    aben
    0.08
    Activations Density 0.019%

    No Known Activations